Here is a demo of a CoreML model I develop to recognize hand signs, running in realtime on iOS camera output. The architecture is a MobileNet v1 classification architecture. The model is 13 Megabytes in size, and the average processing time is 40ms. Accuracy on Dev and test set is 94%!
Dataset location and inspiration was a tutorial from this link:
The demo here is running on an iPhone 6s. The model was architected using Keras, trained on CS230's SIGNS dataset and custom dataset, and converted to coreml using coremltools.
1 comment
[ 301 ms ] story [ 2039 ms ] threadDataset location and inspiration was a tutorial from this link:
https://cs230-stanford.github.io/proj...
The demo here is running on an iPhone 6s. The model was architected using Keras, trained on CS230's SIGNS dataset and custom dataset, and converted to coreml using coremltools.
Code available to train and deploy model here: https://github.com/interactivetech/Ha...
If interested in integrating deep learning to your ios app, feel free to email me at interactivetech1@gmail.com